Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1404bf396016b00b6afb70e65d42e59cbafdc03c1f10969650b62bf34fb5272
+oid sha256:d93ea238464f8245fb8b4e26073133a9c42d4b86041846aa22fa2b9d387e7dda
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e244bd392f4cf38d7baf8eeeb4a0e14862938b6c70f4319110a558f402e0fca
+oid sha256:ced23ed408c1793fd69cb383c82a941035fbe94d76167c422bae1366c24fc57b
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01845062093435837,
+  "epoch": 0.02365464222353637,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 170.688,
       "eval_steps_per_second": 85.344,
       "step": 39
+    },
+    {
+      "epoch": 0.018923713778829097,
+      "grad_norm": 1.8534423361415975e-05,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 46.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.019396806623299824,
+      "grad_norm": 1.61116859089816e-05,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 46.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.01986989946777055,
+      "grad_norm": 2.0304858480812982e-05,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 46.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.02034299231224128,
+      "grad_norm": 2.984837192343548e-05,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 46.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.020816085156712006,
+      "grad_norm": 8.02991689852206e-06,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 46.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.021289178001182733,
+      "grad_norm": 2.4123475668602623e-05,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 46.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.02176227084565346,
+      "grad_norm": 4.200504918117076e-05,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 46.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.022235363690124188,
+      "grad_norm": 1.3180618225305807e-05,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 46.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.022708456534594915,
+      "grad_norm": 1.2039415196340997e-05,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 46.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.023181549379065643,
+      "grad_norm": 7.184164587670239e-06,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 46.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.02365464222353637,
+      "grad_norm": 1.4828357961960137e-05,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 776992260096.0,
+  "total_flos": 996143923200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null